© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14906
    Prev
    Next
    INDEX
    Explanations

    references to time durations and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lengths of time

    np_acts-logits-general · gemini-2.0-flash

    periods of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addPreferredGap
    -0.54
    }))
    -0.53
    /-
    -0.53
    !("{
    -0.52
    migrationBuilder
    -0.52
    }}}\
    -0.52
    ]))
    -0.51
    <bos>
    -0.50
    })).
    -0.50
    ism
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.87
    LayoutStyle
    0.75
    ViewFeatures
    0.75
    HtmlAttribute
    0.74
     hinweg
    0.73
     bune
    0.65
     tillbaka
    0.65
     rând
    0.64
    onViewCreated
    0.64
     mattino
    0.63
    Activations Density 0.161%

    No Known Activations